Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ UPCommons. Portal de...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
versions View all 2 versions
addClaim

Aprendizaje automático para la ciencia de datos

Authors: Manzanera Moreno, Óscar;

Aprendizaje automático para la ciencia de datos

Abstract

El proyecto se centra en una rama específica de la ciencia de datos: el aprendizaje automático. Tiene como propósito diseñar un algoritmo predictivo para cada uno de los cuatro casos que se exponen en el documento. Se utilizan métodos propios del aprendizaje automático y se ejecutan en Python. Se emplea la regresión logística para predecir la victoria o derrota de un conjunto de partidos de baloncesto, el clustering como modelo predictivo no supervisado para agrupar en tres clases a los soldados estadounidenses, los sistemas de recomendación para recomendar series de Netflix a personas desconocidas y, finalmente, el procesamiento del lenguaje natural para leer títulos de libros y clasificarlos por temática. Se mide también la precisión alcanzada de cada algoritmo para comprobar su efectividad.

El projecte es basa en una branca específica de la ciència de dades: l’aprenentatge automàtic. Té com a propòsit dissenyar un algorisme predictiu per cada un dels quatre casos que s’exposen al document. S’utilitzen mètodes propis de l’aprenentatge automàtic i s’executa en Python. S’empra la regressió logística per predir la victòria o derrota d’un conjunt de partits de bàsquet, el clustering com a model predictiu no supervisat per agrupar en tres classes als soldats estatunidencs, els sistemes de recomanació per recomanar sèries de Netflix a persones desconegudes i, finalment, el processament del llenguatge natural per llegir títols de llibres i classificar-los per temàtica. Es mesura també la precisió assolida de cada algorisme per comprovar la seva efectivitat.

The project focuses on a specific branch of data science: machine learning. Its purpose is to design a predictive algorithm for each of the four cases that are exposed in the document. Machine learning methods are used and run in Python. Logistic regression is used to predict the victory or defeat of a set of basketball games, clustering as an unsupervised predictive model to group US Army into three classes, recommendation systems to recommend Netflix series to unknown people and, finally, natural language processing to read book titles and classify them by subject. The achieved precision of each algorithm is also measured to verify its effectiveness.

Country
Spain
Keywords

aprendizaje automático., Àrees temàtiques de la UPC::Enginyeria elèctrica, aprendizaje automático, Machine learning, Aprenentatge automàtic, Algorismes, Algorithms, Ciencia de datos

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green